Member-only story
2022–11–09 | Your Daily AI Research tl;dr 🧠
Deepmind’s new Benchmark for Tracking Any Point in a Video, Video-and-Language Pre-Training and the ML DataOps Summit 2022!
Welcome to your official daily AI research tl;dr (often with code and news) for AI professionals where I share the most exciting papers I find daily, along with a one-liner summary to help you quickly determine if the article (and code) is worth investigating.
1️⃣ TAP-Vid: A Benchmark for Tracking Any Point in a Video
TAP-Vid, a new benchmark for tracking points on physical surfaces in videos!
Link to the paper: https://arxiv.org/pdf/2211.03726.pdf
2️⃣ CLOP: Video-and-Language Pre-Training with Knowledge Regularizations
A simple yet effective Structural Knowledge Prediction (SKP) task to pull together the latent representations of similar videos; and a novel Knowledge-guided sampling approach for Contrastive Learning (KCL) to push apart cross-modal hard negative samples.
Link to the paper: https://arxiv.org/pdf/2211.03314.pdf